Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3664 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2364. Min Range: -6.2364
Max Act: 6.2364. Min Act: -0.1700
Data Index: 7813705 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2364. Min Range: -6.2364
Max Act: 6.1114. Min Act: -0.1700
Data Index: 7876164 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2364. Min Range: -6.2364
Max Act: 5.9239. Min Act: -0.1700
Data Index: 5639188 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2364. Min Range: -6.2364
Max Act: 5.8926. Min Act: -0.1700
Data Index: 2436248 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2364. Min Range: -6.2364
Max Act: 5.8614. Min Act: -0.1700
Data Index: 4558921 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2364. Min Range: -6.2364
Max Act: 5.8614. Min Act: -0.1700
Data Index: 5755236 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2364. Min Range: -6.2364
Max Act: 5.8301. Min Act: -0.1700
Data Index: 2599172 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2364. Min Range: -6.2364
Max Act: 5.8301. Min Act: -0.1700
Data Index: 3717514 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2364. Min Range: -6.2364
Max Act: 5.8301. Min Act: -0.1700
Data Index: 997265 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2364. Min Range: -6.2364
Max Act: 5.8301. Min Act: -0.1700
Data Index: 6630047 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2364. Min Range: -6.2364
Max Act: 5.7676. Min Act: -0.1700
Data Index: 7743945 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2364. Min Range: -6.2364
Max Act: 5.7364. Min Act: -0.1700
Data Index: 3118297 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2364. Min Range: -6.2364
Max Act: 5.7364. Min Act: -0.1700
Data Index: 2247973 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2364. Min Range: -6.2364
Max Act: 5.6426. Min Act: -0.1700
Data Index: 8059420 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2364. Min Range: -6.2364
Max Act: 5.6426. Min Act: -0.1700
Data Index: 7219287 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2364. Min Range: -6.2364
Max Act: 5.6426. Min Act: -0.1700
Data Index: 1666305 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2364. Min Range: -6.2364
Max Act: 5.6426. Min Act: -0.1700
Data Index: 6315414 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2364. Min Range: -6.2364
Max Act: 5.6114. Min Act: -0.1700
Data Index: 258499 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2364. Min Range: -6.2364
Max Act: 5.6114. Min Act: -0.1700
Data Index: 6189419 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2364. Min Range: -6.2364
Max Act: 5.6114. Min Act: -0.1700
Data Index: 5160504 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19